Simplified Complex Joint Diagonalization Algorithm and Source Separation of Breathing Signals

In the present paper, we have treated the Complex Joint Diagonalization (CJD) problem by proposing a non trivial simplified version of an efficient CJD algorithm based on generalized Givens rotation. The novelty of this approach lies in the optimization step used in order to estimate the complex phase of the generalized Givens rotation. Numerical simulations are conducted in order to compare the performance of our algorithm with the major existing solutions. The developed method has been applied to a real-life application that concerns the separation of breathing signals. These signals are obtained by continuous wave radar illuminating two seating and breathing persons. The results show us the effectiveness of the proposed method in separating the breathing signals.